NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GAMW7ZSDS5QRY850D71CD
Run Details
Model:
Inception Mercury
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.0s
Cost:
$0.000220
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
92.35%
Dialogue to Total Word Ratio
(details)
93.0008%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
The dimly lit kitchen of the suburban house smelled of frosting and excitement. Molly: "Bill, kids will be distracted by the cake, so we need a quick window. I’ve mapped the snack table like a treasure map." Bill: "The presents are stacked under the tree, right? We’ll need a ladder or the party clown’s wig to reach them." Molly: "I brought a grappling hook disguised as a cupcake. It’s perfect for scaling the back wall without triggering the alarm." Bill: "Great, but we must avoid the security camera pointed at the entrance. I’ve got a pair of old sunglasses that can blind it for a few seconds." Molly: "And the kids’ party favors are all plastic, so we can swap them for real loot without raising suspicion." Bill: "We’ll also need a distraction. I can set off the clown’s confetti cannon while you slip in and grab the presents." Molly: "Exactly. I’ll use the frosting as a slip surface, and you’ll be the loudest clown to keep the kids entertained." Bill: "All right, let’s rehearse. Remember, timing is everything, and we leave before the cake is cut." Molly: "Deal. We’ll be the most unforgettable thieves at a children's party." The clock ticks loudly, counting down to the chaos now.
created_at
"2026-03-06T12:00:32.322Z"
3/6/2026, 12:00:32 PM
model
"inception/mercury"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4526
moderation_latency
(null)
generation_time
4649
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
71
native_tokens_completion
271
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
4
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0002201
router
(null)
provider_responses
0
endpoint_id
"da1082ea-721e-460e-b330-034ae7aefc7f"
id
"chatcmpl-e5707663-f456-45dd-b139-765ca387f475"
is_byok
false
latency
273
model_permaslug
"inception/mercury"
provider_name
"Inception"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772798432-eFjKnCeUEOqQyOqPjPSn"
upstream_id
"chatcmpl-e5707663-f456-45dd-b139-765ca387f475"
total_cost
0.0002201
cache_discount
9e-7
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
92.35%
Dialogue to Total Word Ratio
Ratio: 84.69%, Deviation: 5.31%
neededClean
false
wordsTotal
209
wordsDialogue
177
93.0008%